EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Realisation of an Application Specific Multispectral Snapshot-Imaging System Based on Multi-Aperture-Technology and Multispectral Machine Learning Loops

Lennard Wunsch iD, Martin Hubold, Rico Nestler iD, Gunther Notni iD

Sensors · 14.12.2024 · 24 (24) · 7984

DOI: 10.3390/s24247984 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 14.12.2024. Verfasst von Lennard Wunsch und 3 weiteren Autor:innen. Beteiligte Einrichtung: Group of Quality Assurance and Industrial Image Processing, Faculty of Mechanical Engineering, Technische Universität Ilmenau, Gustav-Kirchhoff-Platz…. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Projektträger Jülich.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multispectral imaging (MSI) enables the acquisition of spatial and spectral image-based information in one process. Spectral scene information can be used to determine the characteristics of materials based on reflection or absorption and thus their material compositions. This work focuses on so-called multi aperture imaging, which enables a simultaneous capture (snapshot) of spectrally selective and spatially resolved scene information. There are some limiting factors for the spectral resolution when implementing this imaging principle, e.g., usable sensor resolutions and area, and required spatial scene resolution or optical complexity. Careful analysis is therefore needed for the specification of the multispectral system properties and its realisation. In this work we present a systematic approach for the application-related implementation of this kind of MSI. We focus on spectral system modeling, data analysis, and machine learning to build a universally usable multispectral loop to find the best sensor configuration. The approach presented is demonstrated and tested on the classification of waste, a typical application for multispectral imaging.

Schlagwörter

Stichwörter der Autor:innen

feature space evaluationmachine learningmulti-aperture cameramultispectral data analysismultispectral imagingspectral processingspectral sensor modelingwaste classification

Autor:innen und Institutionen

  • Group of Quality Assurance and Industrial Image Processing, Faculty of Mechanical Engineering, Technische Universität Ilmenau, Gustav-Kirchhoff-Platz 2, 98693 Ilmenau, Germany.
  • Fraunhofer Institute for Applied Optics and Precision Engineering IOF Jena, Albert-Einstein-Str. 7, 07745 Jena, Germany.
  • Zentrum für Bild- und Signalverarbeitung e.V., Werner-von-Siemens-Str. 12, 98693 Ilmenau, Germany.

ORCID-Profile: Lennard Wunsch, Rico Nestler, Gunther Notni

Förderung

  • Projektträger Jülich

Zitieren

APA

Wunsch, L., Hubold, M., Nestler, R., & Notni, G. (2024). Realisation of an Application Specific Multispectral Snapshot-Imaging System Based on Multi-Aperture-Technology and Multispectral Machine Learning Loops. Sensors, 24(24), 7984. https://doi.org/10.3390/s24247984

Vancouver

Wunsch L, Hubold M, Nestler R, Notni G. Realisation of an Application Specific Multispectral Snapshot-Imaging System Based on Multi-Aperture-Technology and Multispectral Machine Learning Loops. Sensors. 2024;24(24):7984. doi:10.3390/s24247984

BibTeX
@article{Wunsch2024,
  author = {Wunsch, Lennard and Hubold, Martin and Nestler, Rico and Notni, Gunther},
  title = {Realisation of an Application Specific Multispectral Snapshot-Imaging System Based on Multi-Aperture-Technology and Multispectral Machine Learning Loops},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {24},
  pages = {7984},
  doi = {10.3390/s24247984}
}
Kostenlos starten →